cs.AI（2024-08-10）
📊 共 7 篇论文
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions | 综述：大型语言模型中的隐私保护——威胁与解决方案 | large language model | ||
| 2 | Multi-Agent Planning Using Visual Language Models | 提出基于视觉语言模型的多智能体规划框架，解决具身任务规划中多模态信息融合难题。 | large language model | ||
| 3 | ViC: Virtual Compiler Is All You Need For Assembly Code Search | 提出ViC：利用虚拟编译器进行汇编代码搜索，提升逆向工程效率 | large language model | ||
| 4 | LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale | LLMServingSim：用于大规模LLM推理服务的软硬件协同仿真基础设施 | large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Metacognitive Myopia in Large Language Models | 提出元认知近视理论框架，解释并解决大语言模型中的偏差问题。 | reinforcement learning large language model | ||
| 6 | Exploring Applications of State Space Models and Advanced Training Techniques in Sequential Recommendations: A Comparative Study on Efficiency and Performance | 探索状态空间模型与高级训练技术在序列推荐中的应用，提升效率与性能 | SSM state space model large language model | ||
| 7 | In-Context Exploiter for Extensive-Form Games | 提出ICE：利用上下文学习在扩展式博弈中自适应地利用对手策略 | reinforcement learning curriculum learning |